PyTorch

Tutorial

• https://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html

Examples

MNIST

• https://github.com/pytorch/examples/tree/main/mnist

Tried on 2.3 GHz 8 Core Intel Core i9 with no GPU, 16 GB RAM with python 3.10

date;python main.py --save-model;date
Sa 31 Dez 2022 18:30:38 MST
Train Epoch: 1 [0/60000 (0%)]	Loss: 2.305400
Train Epoch: 1 [640/60000 (1%)]	Loss: 1.359776
Train Epoch: 1 [1280/60000 (2%)]	Loss: 0.842926
Train Epoch: 1 [1920/60000 (3%)]	Loss: 0.593794
Train Epoch: 1 [2560/60000 (4%)]	Loss: 0.366338
Train Epoch: 1 [3200/60000 (5%)]	Loss: 0.469323
Train Epoch: 1 [3840/60000 (6%)]	Loss: 0.265342
Train Epoch: 1 [4480/60000 (7%)]	Loss: 0.287802
Train Epoch: 1 [5120/60000 (9%)]	Loss: 0.584077
Train Epoch: 1 [5760/60000 (10%)]	Loss: 0.223495
...
Train Epoch: 14 [57600/60000 (96%)]	Loss: 0.036891
Train Epoch: 14 [58240/60000 (97%)]	Loss: 0.000181
Train Epoch: 14 [58880/60000 (98%)]	Loss: 0.007485
Train Epoch: 14 [59520/60000 (99%)]	Loss: 0.000201

Test set: Average loss: 0.0258, Accuracy: 9919/10000 (99%)

Sa 31 Dez 2022 18:45:17 MST

Links

• https://stackoverflow.com/questions/tagged/pytorch
• https://github.com/utkuozbulak/pytorch-cnn-visualizations
• https://github.com/facebookresearch/TorchRay